Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    is mortal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Más
    0.47
     Ma
    0.43
     Prü
    0.42
     Já
    0.42
     Ja
    0.40
     lollipop
    0.38
     James
    0.37
     são
    0.37
     providing
    0.36
     sogenannte
    0.36
    POSITIVE LOGITS
     exemplu
    0.43
     несмотря
    0.42
    clearly
    0.41
     mesela
    0.41
    你知道
    0.40
    显然
    0.40
    你會
    0.40
     เงี้ย
    0.40
     EXAMPLE
    0.38
     wouldnt
    0.38
    Act Density 0.256%

    No Known Activations